Prediction of Glass Chemical Composition and Type Identification Based on Machine Learning Algorithms
Source abstract
Abstract
Ancient glass artifacts were susceptible to weathering from the environment, causing changes in their chemical composition, which pose significant obstacles to the identification of glass products. Analyzing the chemical composition of ancient glass has been beneficial for evaluating their weathering status and proposing measures to reduce glass weathering. The objective of this study was to explore the optimal machine learning algorithm for glass type classification based on chemical composition. A set of glass artifact data including color, emblazonry, weathering, and chemical composition was employed and various methods including logistic regression and machine learning techniques were used. The results indicated that a significant correlation (p < 0.05) could only observed between surface weathering and the glass types (high-potassium and lead–barium). Based on the random forest and logistic regression models, the primary chemical components that signify glass types and weathering status were determined using PbO, K2O, BaO, SiO2, Al2O3, and P2O5. The random forest model presented a superior ability to identify glass types and weathering status, with a global accuracy of 96.3%. This study demonstrates the great potential of machine learning for glass chemical component estimation and glass type and weathering status identification, providing technical guidance for the appraisal of ancient glass artifacts.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Hydraulic Science and Engineering, Yangzhou University, Yangzhou 225009, China
College of Mathematical Science, Yangzhou University, Yangzhou 225009, China
Funding
National Natural Science Foundation of China · China Postdoctoral Science Foundation · “Chunhui Plan” Cooperative Scientific Research Project of Ministry of Education of China · Priority Academic Program Development of Jiangsu Higher Education Institutions (PAPD)
References (40)
Show source-provided references
1. Zhou, L. (1984). Major factors affecting the weathering of the silicate glass. J. Dalian Polytech. Univ., 34–44.
2. Tao, Y., Wang, S., and Wang, C. (1993). Effect of zirconium ion injection on the weathering of phosphate glass. Glass Enamel Ophthalmic Opt., 1–6.
3. Nondestructive Analysis of Chemical Composition, Structure and Mineral Phase of Natural Glasses
4. Nondestructive Analysis of the Glass Artifacts of the Han Dynasties Excavated from Guangzhou
5. Wang, L. (2022). High-Efficiency Screening of Zeolite Materials for Adsorption Separation CO2 by Machine Learning, Dalian University of Technology.
6. Theoretical Prediction of Vickers Hardness for Oxide Glasses: Machine Learning Model, Interpretability Analysis, and Experimental Validation10.1016/j.mtla.2024.102006 ↗
7. Liu, F., Shi, J., Wang, W., and Zhao, R. (2022). Review of machine learning algorithm applied in materials science. New Chem. Mater., 50.
8. Zhou, G., Zhang, Z., Feng, R., Zhao, W., Peng, S., Li, J., Fan, F., and Fang, Q. (2023). Chemical Composition Optimization of Biocompatible Non-Equiatomic High-Entropy Alloys Using Machine Learning and First-Principles Calculations. Symmetry, 15.10.3390/sym15112029 ↗
9. Machine Learning Approach for Prediction and Understanding of Glass-Forming Ability10.1021/acs.jpclett.7b01046 ↗
10. Li, J. (2021). Glass Defect Detection Based on Deep Learning, Fujian University of Technology.
11. Glass Defect Recognition Method Based on Integrated Learning
12. Explainability and extrapolation of machine learning models for predicting the glass transition temperature of polymers10.1002/pol.20230714 ↗
13. Machine learning models to predict the residual tensile strength of glass fiber reinforced polymer bars in strong alkaline environments: A comparative study10.1016/j.jobe.2023.106817 ↗
14. Subclass classification and chemical composition analysis and identification of ancient glass products
15. AES and EDX surface analysis of weathered float glass exposed in different environmental conditions10.1016/j.jnoncrysol.2021.121083 ↗
16. Molecular-Composition Analysis of Glass Chemical Composition Based on Time-Series and Clustering Methods10.3390/molecules28020853 ↗
17. Li, Z., Lu, P., Wang, G., Li, J., Yang, Z., Ma, Y., and Wang, H. (2023). Analysis of the Composition of Ancient Glass and Its Identification Based on the Daen-LR, ARIMA-LSTM and MLR Combined Process. Appl. Sci., 13.10.3390/app13116639 ↗
18. Application of Support Vector Machine Algorithm Incorporating Slime Mould Algorithm Strategy in Ancient Glass Classification10.3390/app13063718 ↗
19. Rybacki, P., Niemann, J., Derouiche, S., Chetehouna, S., Boulaares, I., Seghir, N.M., Diatta, J., and Osuch, A. (2024). Convolutional Neural Network (CNN) Model for the Classification of Varieties of Date Palm Fruits (Phoenix dactylifera L.). Sensors, 24.10.3390/s24020558 ↗
20. Research on a classification model of loess seismic landslides based on random forest in the Haiyuan region10.1007/s10064-023-03096-5 ↗
21. A Test of Independence for Two Dimensional Contingency Tables Based on Distance Covariance
22. Based on logistic regression model to determine the weight fuzz comprehensive evaluation method in the application of the slope stability analysis
23. Prediction of reduced glass transition temperature of metallic alloys based on a neural network10.1088/1742-6596/2373/8/082016 ↗
24. Chai, B.X., Eisenbart, B., Nikzad, M., Fox, B., Blythe, A., Bwar, K.H., Wang, J., Du, Y., and Shevtsov, S. (2023). Application of KNN and ANN Metamodeling for RTM Filling Process Prediction. Materials, 16.10.3390/ma16186115 ↗
25. Generative Deep Neural Networks for Inverse Materials Design Using Backpropagation and Active Learning10.1002/advs.201902607 ↗
26. Vehicle Price Prediction System using Machine Learning Techniques
27. Starch-based aerogel prepared by freeze-drying: Establishing a BP neural network prediction model10.1007/s13726-022-01105-0 ↗
28. Source discrimination of mine water based on the random forest method10.1038/s41598-022-24037-4 ↗
29. The accuracy of Random Forest performance can be improved by conducting a feature selection with a balancing strategy10.7717/peerj-cs.1041 ↗
30. Effects of Random Forest Parameters in the Selection of Biomarkers10.1093/comjnl/bxz161 ↗
31. Study on the Importance of Variables Based on Random Forest
32. Research on the composition analysis and identification model of ancient glass products
33. The Robustness of Binary Logistic Regression and Linear Discriminant Analysis for the Classification and Differentiation between Dairy Cows and Buffaloes
34. The Weathering of Silicate Glasses
35. Corrosion mechanisms for lead-barium glass from the Warring States period10.1186/s40494-023-00930-7 ↗
36. On the research of cultural relic restoration under reverse design10.1051/e3sconf/202018903006 ↗
37. The impact of data noise on permanent deformation behaviour of asphalt concrete mixtures10.1080/10298436.2018.1549324 ↗
38. Optimum trim prediction for container ships based on machine learning10.1016/j.oceaneng.2022.111322 ↗
39. Zhou, X., Ma, Y., Luo, Y., Tian, T., Liu, W., Li, X., He, N., Yan, Z., and Ni, H. (2020). Study on Chromatographic Condition Assessment of Transformer Oil Based on Random Forest Model. DEStech Trans. Environ. Energy Earth Sci., 35482.10.12783/dteees/peees2020/35482 ↗
40. Prediction of Original Ingredients of Portland Glass and Research into Subclassification Methods Based on Machine Learning